RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs

• URL: http://arxiv.org/abs/2605.01913v1
• Date: Sun, 03 May 2026 14:48:18 GMT
• Title: RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
• Abstract summary: Fine-tuning safety-aligned language models for downstream tasks can lead to substantial degradation of refusal behavior.<n>We introduce REFUSALGUARD, a representation-level fine-tuning framework that preserves safety-relevant structure during model adaptation.
• Score: 5.100622189286672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded in structured representations within the model's activation space, how these representations change during fine-tuning and why alignment degrades remains poorly understood. In this work, we investigate the representation-level mechanisms underlying alignment degradation. Our analysis shows that standard fine-tuning induces systematic drift in safety-relevant representations, distorts their geometric structure, and introduces interference between task optimization and safety features. These effects collectively lead to increased harmful compliance. Motivated by these findings, we introduce REFUSALGUARD, a representation-level fine-tuning framework that preserves safety-relevant structure during model adaptation. Our approach constrains updates in hidden representation space, ensuring that safety-mediating components remain stable while allowing task-specific learning in complementary directions. We evaluate REFUSALGUARD across multiple model families, including LLaMA, Gemma, and Qwen, on adversarial safety benchmarks such as AdvBench, DirectHarm4, and JailbreakBench, as well as downstream utility tasks. Our approach achieves attack success rates comparable to base safety-aligned models while maintaining competitive task performance, significantly outperforming baselines.

Related papers

• Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection [21.411964269762432]
  We present a comprehensive framework for diagnosing and repairing unsafe channels within Large Vision-Language Models (LVLMs)<n>We first perform causal mediation analysis to identify neurons and layers that are causally responsible for unsafe behaviors.<n>We introduce a dual-modal safety subspace projection method that learns generalized safety subspaces for both visual and textual modalities.
  arXiv  Detail & Related papers  (2026-03-28T11:31:16Z)
• HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task [42.665798473119516]
  We propose an architecture-agnostic safeguard featuring Context-Guided Chain-of-Thought (CG-CoT)<n>CG-CoT decomposes risk assessment into active perception that sequentially anchors attention to interaction targets and relevant spatial neighborhoods.<n> Experiments demonstrate that our model HomeGuard significantly enhances safety, improving risk match rates by over 30% compared to base models.
  arXiv  Detail & Related papers  (2026-03-15T13:09:43Z)
• Enhancing Safety of Large Language Models via Embedding Space Separation [24.821172423424866]
  Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge.<n>Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs typically exhibit linear separability.<n>Motivated by this observation, we propose a representation-level fine-tuning approach, named Embedding Space Separation (ES2)
  arXiv  Detail & Related papers  (2026-03-01T07:22:38Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge [51.634837361795434]
  SaFeR-CLIP reconciles safety and performance, recovering up to 8.0% in zero-shot accuracy over prior methods.<n>We also contribute NSFW-Caps, a new benchmark of 1,000 highly-aligned pairs for testing safety under distributional shift.
  arXiv  Detail & Related papers  (2025-11-20T19:00:15Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• Probing the Robustness of Large Language Models Safety to Latent Perturbations [30.16804362984161]
  Safety alignment is a key requirement for building reliable Artificial General Intelligence.<n>We observe that minor latent shifts can still trigger unsafe responses in aligned models.<n>We introduce Layer-wise Adversarial Patch Training(LAPT), a fine-tuning strategy that injects controlled perturbations into hidden representations during training.
  arXiv  Detail & Related papers  (2025-06-19T07:03:05Z)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• LookAhead Tuning: Safer Language Models via Partial Answer Previews [62.529794567687354]
  Fine-tuning enables large language models to adapt to specific domains, but often compromises their previously established safety alignment.<n>We introduce LookAhead Tuning, a lightweight and effective data-driven approach that preserves safety during fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T18:11:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.